Early detection of superficial squamous cell carcinoma in the head and neck region and esophagus by narrow band imaging: a multicenter randomized controlled trial

Deep Learning for the Diagnosis of Esophageal Cancer in Endoscopic Images: A Systematic Review and Meta-Analysis

Esophageal cancer, one of the most common cancers with a poor prognosis, is the sixth leading cause of cancer-related mortality worldwide. Early and accurate diagnosis of esophageal cancer, thus, plays a vital role in choosing the appropriate treatment plan for patients and increasing their survival rate. However, an accurate diagnosis of esophageal cancer requires substantial expertise and experience. Nowadays, the deep learning (DL) model for the diagnosis of esophageal cancer has shown promising performance. Therefore, we conducted an updated meta-analysis to determine the diagnostic accuracy of the DL model for the diagnosis of esophageal cancer. A search of PubMed, EMBASE, Scopus, and Web of Science, between 1 January 2012 and 1 August 2022, was conducted to identify potential studies evaluating the diagnostic performance of the DL model for esophageal cancer using endoscopic images. The study was performed in accordance with PRISMA guidelines. Two reviewers independently assessed potential studies for inclusion and extracted data from retrieved studies. Methodological quality was assessed by using the QUADAS-2 guidelines. The pooled accuracy, sensitivity, specificity, positive and negative predictive value, and the area under the receiver operating curve (AUROC) were calculated using a random effect model. A total of 28 potential studies involving a total of 703,006 images were included. The pooled accuracy, sensitivity, specificity, and positive and negative predictive value of DL for the diagnosis of esophageal cancer were 92.90%, 93.80%, 91.73%, 93.62%, and 91.97%, respectively. The pooled AUROC of DL for the diagnosis of esophageal cancer was 0.96. Furthermore, there was no publication bias among the studies. The findings of our study show that the DL model has great potential to accurately and quickly diagnose esophageal cancer. However, most studies developed their model using endoscopic data from the Asian population. Therefore, we recommend further validation through studies of other populations as well.

Expected value of artificial intelligence in gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement

This ESGE Position Statement defines the expected value of artificial intelligence (AI) for the diagnosis and management of gastrointestinal neoplasia within the framework of the performance measures already defined by ESGE. This is based on the clinical relevance of the expected task and the preliminary evidence regarding artificial intelligence in artificial or clinical settings. MAIN RECOMMENDATIONS:: (1) For acceptance of AI in assessment of completeness of upper GI endoscopy, the adequate level of mucosal inspection with AI should be comparable to that assessed by experienced endoscopists. (2) For acceptance of AI in assessment of completeness of upper GI endoscopy, automated recognition and photodocumentation of relevant anatomical landmarks should be obtained in ≥90% of the procedures. (3) For acceptance of AI in the detection of Barrett's high grade intraepithelial neoplasia or cancer, the AI-assisted detection rate for suspicious lesions for targeted biopsies should be comparable to that of experienced endoscopists with or without advanced imaging techniques. (4) For acceptance of AI in the management of Barrett's neoplasia, AI-assisted selection of lesions amenable to endoscopic resection should be comparable to that of experienced endoscopists. (5) For acceptance of AI in the diagnosis of gastric precancerous conditions, AI-assisted diagnosis of atrophy and intestinal metaplasia should be comparable to that provided by the established biopsy protocol, including the estimation of extent, and consequent allocation to the correct endoscopic surveillance interval. (6) For acceptance of artificial intelligence for automated lesion detection in small-bowel capsule endoscopy (SBCE), the performance of AI-assisted reading should be comparable to that of experienced endoscopists for lesion detection, without increasing but possibly reducing the reading time of the operator. (7) For acceptance of AI in the detection of colorectal polyps, the AI-assisted adenoma detection rate should be comparable to that of experienced endoscopists. (8) For acceptance of AI optical diagnosis (computer-aided diagnosis [CADx]) of diminutive polyps (≤5 mm), AI-assisted characterization should match performance standards for implementing resect-and-discard and diagnose-and-leave strategies. (9) For acceptance of AI in the management of polyps ≥ 6 mm, AI-assisted characterization should be comparable to that of experienced endoscopists in selecting lesions amenable to endoscopic resection.

Long-term Incidence Rates of Esophageal Squamous Cell Carcinoma in Chinese Patients With Low-grade Intraepithelial Neoplasia and Association of Surveillance Endoscopy With Incidence

IMPORTANCE

Surveillance endoscopy is recommended for patients with low-grade intraepithelial neoplasia (LGIN); high-quality evidence about the use of surveillance endoscopy and esophageal squamous cell carcinoma (ESCC) incidence in patients with LGIN is important but limited.

OBJECTIVE

To estimate long-term ESCC incidence rates in patients with LGIN and the association between surveillance endoscopy and ESCC incidence.

DESIGN, SETTING, AND PARTICIPANTS

This community-based, multicenter, prospective cohort study in 9 regions in rural China included patients with LGIN diagnosed by endoscopic screening between July 1, 2007, and December 31, 2016; all participants were followed up until December 31, 2021.

MAIN OUTCOMES AND MEASURES

The primary outcome was ESCC incidence. The ESCC standardized incidence ratio (SIR) was estimated using sex- and age-specific incidence in the general population of rural China in 2010 and hazard ratios (HRs) and 95% CIs were calculated using Cox proportional hazards models.

RESULTS

A total of 3258 patients with LGIN were included; 1772 (54.39%) were men, with a mean (SD) age of 58.21 (6.97) years. Among them, 1378 patients (42.30%) underwent at least 1 surveillance endoscopy (surveillance group) and 1880 (57.70%) did not undergo any surveillance endoscopy (nonsurveillance group). During the follow-up period (median, 7.96 years; IQR, 6.08-10.54 years), 170 ESCC cases were diagnosed, with a cumulative incidence of 6.28 per 1000 person-years. A higher incidence of ESCC (incidence rate, 7.07 per 1000 person-years) was observed in the nonsurveillance group than in the surveillance group (incidence rate, 5.14 per 1000 person-years). Patients with LGIN in the surveillance group had a lower SIR (SIR, 4.07; 95% CI, 1.13-10.34) than those in the nonsurveillance group (SIR, 5.65; 95% CI, 2.00-12.58); however, patients with LGIN in both groups had a higher risk of ESCC than the general population. Patients in the surveillance group had a 31% decreased risk of ESCC incidence (HR, 0.69; 95% CI, 0.50-0.95) compared with those in the nonsurveillance group, after adjusting for baseline risk factors.

CONCLUSIONS AND RELEVANCE

In this prospective cohort study, patients with LGIN had a higher risk of developing ESCC than the general population, and endoscopic surveillance was associated with a decrease in ESCC incidence in these patients.

Using texture and colour enhancement imaging to evaluate gastrointestinal diseases in clinical practice: a review

White light imaging (WLI) is the most common endoscopic technique used for screening of gastrointestinal diseases. However, despite the advent of a new processor that offers sufficient clear illumination and other advanced developments in endoscopic instrumentation, WLI alone is inadequate for detecting all gastrointestinal diseases with abnormalities in mucosal discoloration and morphological changes to the mucosal surface. The recent development of image-enhanced endoscopy (IEE) has dramatically improved the detection of gastrointestinal diseases. Texture and colour enhancement imaging (TXI) is a new type of IEE that enhances brightness, surface irregularities, such as elevations or depressions, and subtle colour changes. TXI with two modes, namely modes 1 and 2, can selectively enhance brightness in dark areas of an endoscopic image and subtle tissue differences such as slight morphological or colour changes while simultaneously preventing over-enhancement. Several clinical studies have investigated the efficacy of TXI for detecting and visualizing gastrointestinal diseases, including oesophageal squamous cell carcinoma (ESCC), Barret's epithelium, gastric cancer, gastric mucosal atrophy and intestinal metaplasia. Although TXI is often more useful for detecting and visualizing gastrointestinal diseases than WLI, it remains unclear whether TXI outperforms other IEEs, such as narrow-band imaging (NBI), in similar functions, and whether the performance of TXI modes 1 and 2 are comparable. Therefore, large-scale prospective studies are needed to compare the efficacy of TXI to WLI and other IEEs for endoscopic evaluation of patients undergoing screening endoscopy. Here, we review the characteristics and efficacy of TXI for the detection and visualization of gastrointestinal diseases.Key MessagesTXI mode 1 can improve the visibility of gastrointestinal diseases and qualitative diagnosis, especially for diseases associated with colour changes.The enhancement of texture and brightness with TXI mode 2 enables the detection of diseases, and is ideal for use in the first screening of gastrointestinal tract.

The Advantage of Immunohistochemical Staining for Evaluating Lymphovascular Invasion Is Limited for Patients with Esophageal Squamous Cell Carcinoma Invading the Muscularis Mucosa

The cumulative metastasis rate of esophageal squamous cell carcinoma (ESCC) pathologically invading the muscularis mucosae (pT1a-MM), based on lymphovascular invasion (LVI) evaluated by immunohistochemical (IHC) staining is unknown. This retrospective study included patients with endoscopically resected pT1a-MM ESCC. The primary endpoint was the metastasis rate of pT1a-MM based on LVI, evaluated using IHC and additional prophylactic therapy. The secondary endpoint was the identification of independent factors for metastasis based on lesion characteristics. The prognosis was also analyzed considering the impact of head and neck cancer. A total of 104 patients were analyzed, with a median follow-up of 74 months. The positive rate for LVI was 43.3% (45/104). In 33 patients, IHC was not performed at the time of clinical evaluation, 8 of whom exhibited LVI. However, these patients did not exhibit metastasis. The metastasis rates of patients without LVI, those with LVI and additional therapy, and those with LVI without additional therapy were 5.1%, 20.8%, and 0%, respectively. Lesion size ≥ 25 mm was the only independent factor for metastasis in multivariate analysis. The advantage of IHC for determining additional prophylactic therapy is limited for patients with pT1a-MM ESCC.

Advanced Endoscopy for Benign Esophageal Disease: A Review Focused on Non-Erosive Reflux Disease and Eosinophilic Esophagitis

Advanced endoscopy (AVE) techniques include image-enhanced endoscopy methods, such as narrow-band imaging (NBI), and types of microscopic endoscopy, such as endocytoscopy. In the esophagus, AVE first showed diagnostic utility in the diagnosis of superficial esophageal cancer and was then applied to inflammatory disease. This review focuses on non-erosive reflux disease (NERD) and eosinophilic esophagitis (EoE), which sometimes show no abnormal findings on standard white light endoscopy alone. Studies have demonstrated that advanced endoscopy, including NBI magnification endoscopy and endocytoscopy, improved the diagnostic performance of white-light endoscopy alone for NERD and EoE. In this review, we explain why advanced endoscopy is needed for the diagnosis of these esophageal inflammatory diseases, summarize the study results, and discuss future perspectives.

Prognostic significance of systemic inflammatory response markers in patients with superficial esophageal squamous cell carcinomas

Endoscopic resection or esophagectomy has becoming the standard treatment for superficial esophageal squamous cell carcinomas (SESCC), but some patients may develop disease progression or second primary cancers after the therapies. Neutrophil to lymphocyte ratio (NLR), lymphocyte to monocyte ratio (LMR), and platelet to lymphocyte ratio (PLR) reflect the balance between pro-cancer inflammatory and anti-cancer immune responses, however their roles in SESCC are still unknown. We consecutively enrolled patients with newly diagnosed SESCC (clinical stage Tis or T1N0M0) who were treated at our institute. Pre-treatment NLR, LMR and PLR were assessed and then correlated with clinical factors and long-term survival. A total of 156 patients were enrolled (152 males, 4 females; median age: 52.2 years), of whom 104 received endoscopic resection and 52 were treated with esophagectomy or chemoradiation.. During a mean follow-up period of 60.1 months, seventeen patients died of ESCCs, and 45 died of second primary cancers. The 5-year ESCC-specific survival and 5-year overall survival rate were 86% and 57%, respectively. LMR (P < 0.05) and NLR (P < 0.05), but not PLR were significantly correlated with overall survival. Receiver operating characteristic curve analysis showed optimal LMR and NLR cut-off values of 4 and 2.5, respectively, to predict a poor prognosis. Patients with a high NLR or low LMR tended to have longer tumor length, larger circumferential extension, and presence of second primary cancers. Multivariate Cox regression analysis showed that presence of second primary cancers (HR: 5.05, 95%CI: 2.75-9.28), low LMR (HR: 2.56, 95%CI: 1.09-6.03) were independent risk factors for poor survival. A low pre-treatment LMR may be a non-invasive pretreatment predictor of poor prognosis to guide the surveillance program, suggesting that anti-cancer immunity may play a role in the early events of esophageal squamous cancer.

Trans-oral trans-sheath forceps biopsy for patients with severe esophageal obstruction under fluoroscopy

To investigate the safety and effectiveness of trans-oral trans-sheath forceps biopsy (TTFB) for patients with severe esophageal obstruction under fluoroscopy. From November 2016 to November 2019, 35 patients with level III or IV dysphagia and a Karnofsky score of less than 60 were enrolled to undergo TTFB and esophageal nutrition tube insertion or stenting simultaneously. Data on diagnostic performance, early complications, and radiation dose were collected, and Karnofsky scores before and after the procedures were compared. The technical success of TTFB was 100%. The sensitivity, specificity and accuracy were 92.3% (24/26), 77.8% (7/9), and 88.6% (31/35), respectively. Complications occurred in two cases (5.7%). The mean procedure duration and irradiation dose were 23.2 min and 7.2 mSv, respectively. The Karnofsky scores significantly increased after 2-4 weeks (t = 11.22, P < 0.0001). TTFB is a safe and effective method for patients with severe esophageal obstruction under fluoroscopy, especially in those who cannot undergo or refuse endoscopy.

Effectiveness of screening endoscopy for esophageal squamous cell carcinoma in Japanese males

BACKGROUND

Esophageal squamous cell carcinoma (ESCC) has a poor prognosis; therefore, early detection is essential. In Japan, more than 90% of esophageal cancers are ESCC. Endoscopy is effective to detect ESCC in the early stage, but there is a limited number of reports examining its efficacy and effectiveness.

OBJECTIVE

This study aimed to evaluate the efficacy of screening endoscopy for detecting ESCC.

METHODS

This retrospective study analyzed the prevalence of ESCC, annual transition of prevalence, and the stage of each ESCC among 128,520 medical check-up patients who underwent esophagogastroduodenoscopy from April 2015 to March 2020 at Yamanashi Koseiren Health Care Center. Furthermore, a case-control study utilized the multivariate logistic regression analysis was performed to assess the risk factor of ESCC.

RESULTS

Among a total of 128,520 subjects, 42 ESCC patients were detected, with 95.2% being diagnosed at early stages. Annual prevalence in males was 0.015% (2/13,122) in 2015, 0.044% (6/13,562) in 2016, 0.044% (6/13,676) in 2017, 0.074% (10/13,488) in 2018%, and 0.11% (16/14,386) in 2019. ESCC prevalence has been increasing each year. A significant increase was observed between 2015 and 2018 (p = 0.039). ESCC prevalence was 0.102% (25/24,272) when focusing on males aged over 50 years with a history of smoking and drinking. Regarding the case-control study, the multivariate logistic regression analysis revealed smoking (p = 0.044), mean corpuscular volume (MCV) (p = 0.0018), and severe gastric atrophy (p = 0.048) as positively correlated with ESCC.

CONCLUSION

In conclusion, ESCC has been increasing in our center from 2015 to 2019, and the prevalence has been approaching that of gastric cancer in 2019 in male subjects. ESCC can be detected efficiently by targeting males with high MCV who have a history of drinking and smoking.

A Recurrence Predictive Model for Node-negative Esophageal Squamous Cell Carcinoma After Upfront Esophagectomy

The prognosis for pathologically node-negative (pN0) esophageal squamous cell carcinoma (ESCC) with surgery alone remains poor. We aimed to develop a model for a more precise prediction of recurrence, which will allow personalized management for pN0 ESCC after upfront complete resection. Clinical and pathological records of patients with completely resected pT1-3N0M0 ESCC were retrospectively analyzed between January 2014 and December 2019. A nomogram for the prediction of recurrence was established based on the Cox regression analysis and evaluated by C-index, AUC, and calibration curves. The model was further validated using bootstrap resampling and k-fold cross-validation and compared with the 8th edition of the AJCC TNM staging system using Td-ROC, NRI, IDI, and DCA. Two-hundred-and seventy cases were included in this study. The median follow-up was 45 months. Distant and/or loco-regional recurrences were noted in 89 (33.0%) patients. The predictive model revealed pT-category, differentiation, perineural invasion, examined lymph nodes (ELN), and prognostic nutritional index (PNI) as independent risk factors for recurrence, with a c-index of 0.725 in the bootstrapping cohort. Td-ROC, NRI, and IDI showed a better predictive ability than the AJCC 8th TNM staging system. Based on this model, patients in the low-risk group had a significantly lower recurrence incidence than those in the high-risk group (p < .001). The predictive model developed in this study may facilitate the precise prediction of recurrences for pN0 ESCC after upfront surgery. Stratifying management of those patients might bring significantly better survival benefits.

Development and clinical usefulness of a unique red dichromatic imaging technology in gastrointestinal endoscopy: A narrative review

Image-enhanced endoscopy (IEE) allows real-time high-contrast imaging of a targeted lesion without any special equipment. Among various IEE technologies, narrow-band imaging, in which a light of shorter wavelength is used, emphasizes the surface and blood vessel patterns on the mucosal surface. This technology has been widely used in endoscopic diagnosis in the gastrointestinal tract. Red dichromatic imaging (RDI) was recently developed; it utilizes lights of longer wavelengths (520-550, 595-610, and 620-640 nm), which have weak light scattering characteristics in contrast to narrow-band imaging. RDI was designed to enhance the visibility of deep-lying blood vessels and areas of bleeding, and it has been installed in the latest Olympus endoscopy system, EVIS X1, as an advanced version of the optical-digital method that was originally developed. Improving the visibility of deep blood vessels allows more accurate evaluation of esophageal varices and the degree of inflammation in ulcerative colitis. Easier identification of a bleeding source makes hemostasis quicker and easier to accomplish during endoscopic resection procedures such as endoscopic submucosal dissection and peroral endoscopic myotomy as well as during treatment of gastrointestinal bleeding from a peptide ulcer or colon diverticulum. The authors herein review the technological development and principles, review the existing literature on RDI, and discuss the utility and effectiveness of this unique IEE technology in gastrointestinal endoscopy.

Management of Superficial Esophageal Squamous Cell Carcinoma and Early Gastric Cancer following Non-Curative Endoscopic Resection

According to the European and Japanese guidelines, additional treatment is recommended for cases of superficial esophageal squamous cell carcinoma (ESCC) and early gastric cancer (EGC) that do not meet the curability criteria for endoscopic resection (ER), i.e., non-curative ER, owing to the risk of lymph node metastasis (LNM). However, the rates of LNM in such cases were relatively low (e.g., 8% for EGC). Several recent advances have been made in this field. First, pathological risk stratification for metastatic recurrence following non-curative ER without additional treatment was developed for both superficial ESCC and EGC. Second, the pattern of metastatic recurrence and prognosis after recurrence following non-curative ER without additional treatment was found to be considerably different between superficial ESCC and EGC. Third, a combination of ER and selective chemoradiotherapy was developed as a minimally invasive treatment method for clinical T1b-SM ESCC. These findings may help clinicians decide the treatment strategy for patients following non-curative ER; however, for optimal therapeutic decision-making in such patients, it is also important to predict the prognosis other than SESCC or EGC and impaired quality of life. Thus, a novel algorithm that considers these factors, as well as metastatic recurrence, should be developed.

Outcomes of Endoscopic Submucosal Dissection for Treatment of Superficial Pharyngeal Cancers: Systematic Review and Meta-Analysis

BACKGROUND AND AIMS

Studies evaluating the role of endoscopic submucosal dissection (ESD) in the management of superficial pharyngeal cancers have reported promising results. This meta-analysis evaluates the efficacy and safety of ESD in the management of superficial pharyngeal cancers.

METHODS

We reviewed several databases from inception to September 03, 2020, to identify studies evaluating the efficacy and safety of ESD in the management of superficial pharyngeal cancers. Our outcomes of interest were en bloc resection rate, complete resection rate, adverse events, and rates of local recurrence. Pooled rates with 95% confidence intervals (CI) for all outcomes were calculated using random-effect model. Heterogeneity was assessed by I² statistic. We assessed publication bias by using funnel plots and Egger's test. We conducted meta-regression analysis to explore heterogeneity in analyses.

RESULTS

Ten studies were included in analyses. All studies were from Asia. Pooled rates (95% CI) for en bloc resection and complete resection were 94% (87%, 97%) and 72% (62%, 80%), respectively. The pooled rates (95% CI) for adverse events and local recurrence were 10% (5%, 17%) and 1.9% (0.9%, 4%), respectively. Most of the analyses were limited by substantial heterogeneity. On meta-regression analysis, the heterogeneity was explained by size of tumor and histology. Funnel plots and Egger's test showed no evidence of publication bias.

CONCLUSIONS

This meta-analysis including studies from Asian countries demonstrated that ESD is an efficacious and safe option in the management of superficial pharyngeal cancers. More studies and studies from Western countries are needed to further validate these findings.

Assessment of Outcomes From 1-Year Surveillance After Detection of Early Gastric Cancer Among Patients at High Risk in Japan

IMPORTANCE

Single endoscopic examination often misses early gastric cancer (GC), even when both high-definition white light imaging and narrow-band imaging are used. It is unknown whether new GC can be detected approximately 1 year after intensive index endoscopic examination.

OBJECTIVE

To examine whether new GC can be detected approximately 1 year after intensive index endoscopic examination using both white light and narrow-band imaging.

DESIGN, SETTING, AND PARTICIPANTS

This case-control study was a preplanned secondary analysis of a randomized clinical trial involving 4523 patients with a high risk of GC who were enrolled between October 1, 2014, and September 22, 2017. Data were analyzed from December 26, 2019, to April 21, 2021. Participants in the clinical trial received index endoscopy to detect early GC via 2 examinations of the entire stomach using white light and narrow-band imaging. The duration of follow-up was 15 months. The secondary analysis included 107 patients with newly detected GC (case group) and 107 matched patients without newly detected GC (control group) within 15 months after index endoscopy.

INTERVENTIONS

Surveillance endoscopy was scheduled between 9 and 15 months after index endoscopy. If new lesions suspected of being early GC were detected during surveillance endoscopy, biopsies were obtained to confirm the presence of cancer.

MAIN OUTCOMES AND MEASURES

The primary end point was the rate of new GC detected within 15 months after index endoscopy. The main secondary end point was identification of risk factors associated with new GC detected within 15 months after index endoscopy.

RESULTS

Among 4523 patients (mean [SD] age, 70.6 [7.5] years; 3527 men [78.0%]; all of Japanese ethnicity) enrolled in the clinical trial, 4472 received index endoscopy; the rate of early GC detected on index endoscopy was 3.0% (133 patients). Surveillance endoscopy was performed in 4146 of 4472 patients (92.7%) who received an index endoscopy; the rate of new GC detected within 15 months after index endoscopy was 2.6% (107 patients). Among 133 patients for whom early GC was detected during index endoscopy, 110 patients (82.7%) received surveillance endoscopy within 15 months after index endoscopy; the rate of newly detected GC was 10.9% (12 patients). For the secondary analysis of risk factors associated with newly detected GC, characteristics were well balanced between the 107 patients included in the case group vs the 107 patients included in the matched control group (mean [SD] age, 71.7 [7.2] years vs 71.8 [7.0] years; 94 men [87.9%] in each group; 82 patients [76.6%] vs 87 patients [81.3%] with a history of gastric neoplasm). Multivariate analysis revealed that the presence of open-type atrophic gastritis (odds ratio, 6.00; 95% CI, 2.25-16.01; P < .001) and early GC detection by index endoscopy (odds ratio, 4.67; 95% CI, 1.08-20.21; P = .04) were independent risk factors associated with new GC detection.

CONCLUSIONS AND RELEVANCE

In this study, the rate of new GC detected by surveillance endoscopy approximately 1 year after index endoscopy was similar to that of early GC detected by index endoscopy. These findings suggest that 1-year surveillance is warranted for patients at high risk of GC.

Endoscopic Management of Esophageal Cancer

Advances in technology and improved understanding of the pathobiology of esophageal cancer have allowed endoscopy to serve a growing role in the management of this disease. Precursor lesions can be detected using enhanced diagnostic modalities and eradicated with ablation therapy. Furthermore, evolution in endoscopic resection has provided larger specimens for improved diagnostic accuracy and offer potential for cure of early esophageal cancer. In patients with advanced esophageal cancer, endoluminal therapy can improve symptom burden and provide therapeutic options for complications such as leaks, perforations, and fistulas. The purpose of this review article is to highlight the role of endoscopy in the diagnosis, treatment, and palliation of esophageal cancer.

A comparative study of demarcation line diagnostic performance between non-magnifying observation with white light and non-magnifying observation with narrow-band light for early gastric cancer

BACKGROUND AND AIMS

With the improvement in endoscopic equipment functions, narrow-band imaging (NBI) for endoscopic observation of the stomach, which is an organ with a large lumen, is now feasible. Studies evaluating the NBI utility without magnifying endoscopy to diagnose the invasion extent for the demarcation line identification in early gastric cancer have not been reported. This study aimed to investigate the demarcation line diagnostic performance of NBI in early gastric cancer compared to that of white-light imaging (WLI) using prospectively collected consecutive specimens from early gastric cancer patients.

METHODS

Thirty consecutive lesions were collected from patients who underwent endoscopic submucosal dissection for early gastric cancer. Next, 30 NBI and 30 WLI images, each with the same degree of gastric wall extension, angle, and layout for one lesion, were selected, and a total of 60 images were prepared for testing. The early gastric cancer invasion ranges in the endoscopic images was plotted using the web-developed software, and 264 independent endoscopists, unaware of the diagnosis, performed the web tests, with the concordance rates between the ranges of responses. After estimating the actual early gastric cancer invasion ranges, the NBI and WLI results were compared.

RESULTS

The concordance rates for NBI and WLI images were 43.1% (95% confidence interval [CI] 42.5-43.7%) and 37.2% (95% CI 36.6-37.7%), respectively, showing that the concordance rate for NBI was significantly higher than that for WLI.

CONCLUSION

This study suggested that NBI was more useful for identifying demarcation lines than WLI.

Comprehensive risk evaluation for metachronous carcinogenesis after endoscopic submucosal dissection of superficial pharyngeal squamous cell carcinoma

BACKGROUND

Pharyngeal squamous cell carcinoma (PSCC) is associated with a high likelihood of metachronous carcinogenesis, which is known to have a poor prognosis. This study aimed to identify comprehensive risk evaluation indicators for metachronous carcinogenesis after endoscopic submucosal dissection (ESD) of superficial PSCC.

METHODS

The risk of metachronous carcinogenesis was evaluated in 144 patients with superficial PSCC (with no history of PSCC or esophageal squamous cell carcinoma) who underwent initial ESD from 2008 to 2020. Multiple lugol-voiding lesions (LVLs) in the background pharyngeal and esophageal epithelium were evaluated as endoscopic indicators. The hemoglobin, albumin, lymphocyte, and platelet (HALP) score was analyzed as a serum marker.

RESULTS

The median follow-up period was 4.3 years. The coincidence rate for pharyngeal and esophageal LVL grade was 55%. The cumulative 3-year metachronous PSCC rate was 18.9%. The cumulative 3-year second metachronous PSCC rate was 43.9%. Forward stepwise multivariate Cox proportional hazards regression analysis identified pharyngeal LVL grade and a lower HALP score as significant independent predictors. Pharyngeal LVL grade was superior to esophageal LVL grade as a predictor of metachronous PSCC. A lower HALP score was significantly associated with younger age in forward stepwise multivariate logistic regression analysis.

CONCLUSIONS

Patients with a history of superficial PSCC remain at risk for metachronous carcinogenesis over time, and long-term follow-up is imperative. Comprehensive evaluation of endoscopic features with a novel serum marker, namely, the HALP score, can help predict metachronous carcinogenesis.

Endoscopic submucosal dissection without intubation for superficial pharyngeal cancer in a post-total laryngectomy patient

Watch a video of this article.

Swallowing function after transoral surgery for laryngopharyngeal cancer

Transoral surgery (TOS) has been widely used to treat laryngopharyngeal cancers. Although TOS is a minimally invasive procedure, postoperative complications, such as postoperative dysphagia, may occur, which can lead to a poor quality of life for patients undergoing TOS. This study aimed to investigate factors that may affect swallowing function in patients who underwent TOS for laryngopharyngeal cancers. Swallowing function of 84 patients who underwent endoscopic resection for oropharyngeal, hypopharyngeal, and supraglottic lesions was evaluated by the Functional Outcome Swallowing Scale, and predictors for postoperative dysphagia were identified. Multivariate analysis identified the following factors as independent predictors for postoperative dysphagia: Eastern Cooperative Oncology Group Performance Status (ECOG PS, p = 0.008), prior neck radiation therapy (p = 0.008), and operative time (p = 0.021). This study suggests that patients with poor ECOG PS or those who received prior neck radiation therapy should be fully assessed for preoperative swallowing function. In the future, we would like to clarify the criteria for preoperative swallowing evaluation to create a system that can identify patients suitable for TOS.

Is 2045 the best we can do? Mitigating the HPV-related oropharyngeal cancer epidemic

INTRODUCTION

Oropharyngeal cancer (OPC) will be among the most common cancers in men by 2045 due to a rapid rise in human papillomavirus (HPV)-related OPC. Those who survive their cancer often suffer life-long treatment effects and early death. HPV vaccination could prevent virtually all HPV-related cancers but is not an effective preventive strategy for those already exposed. Without a dramatic increase in vaccine uptake in the U.S., HPV vaccination will have a negligible effect on OPC incidence through 2045 and no substantial impact until 2060. Additionally, targeted screening for earlier diagnosis may soon be feasible for those inadequately protected by vaccination.

AREAS COVERED

PubMed search for English-language articles related to incidence, screening, and prevention of HPV-related malignancies, focused on OPC in the U.S.

EXPERT OPINION

HPV-related OPC incidence will continue to increase for the foreseeable future with prophylactic vaccination offering no substantial public health impact for decades. Consequently, we must rapidly increase vaccination rates and develop screening methods to identify high-risk individuals. Such individuals would be eligible for potential preventive treatments and screening to diagnose early-stage HPV-related OPC allowing less morbid treatments. These methods will bridge the population into an era of decreasing incidence after vaccination takes effect.

Outcomes of endoscopic submucosal dissection for superficial esophageal neoplasms in patients with liver cirrhosis

Background/Aims

The treatment of superficial esophageal neoplasms (SENs) in cirrhotic patients is challenging and rarely investigated. We evaluated the outcomes of endoscopic submucosal dissection (ESD) to determine the efficacy and safety of treating SENs in patients with liver cirrhosis.

Methods

The baseline characteristics and treatment outcomes of patients who underwent ESD for SENs between November 2005 and December 2017 were retrospectively reviewed.

Results

ESD was performed in 437 patients with 481 SENs, including 15 cirrhotic patients with 17 SENs. En bloc resection (88.2% vs. 97.0%) and curative resection (64.7% vs. 78.9%) rates were not different between the cirrhosis and non-cirrhosis groups (p=0.105 and p=0.224, respectively). Bleeding was more common in cirrhotic patients (p=0.054), and all cases were successfully controlled endoscopically. The median procedure and hospitalization duration did not differ between the groups. Overall survival was lower in cirrhotic patients (p=0.003), while disease-specific survival did not differ between the groups (p=0.85).

Conclusions

ESD could be a safe and effective treatment option for SENs in patients with cirrhosis. Detailed preprocedural assessments are needed, including determination of liver function, esophageal varix status, and remaining life expectancy, to identify patients who will obtain the greatest benefit.

Definition of Mucosal Breaks in the Era of Magnifying Endoscopy with Narrow-Band Imaging

Background

Gastroesophageal reflux disease is diagnosed endoscopically based on the presence of mucosal breaks. However, mucosal breaks can be judged differently depending on the endoscopist, even in the same image. We investigated how narrow-band imaging (NBI) and magnified endoscopy affect the judgment of mucosal breaks.

Methods

A total of 43 consecutive patients were enrolled who had suspected mucosal breaks on white-light images (WLI) and underwent nonmagnified NBI (N-NBI) and magnified NBI (M-NBI) by a single endoscopist. From WLI, N-NBI, and M-NBI, 129 image files were created. Eight endoscopists reviewed the image files and judged the presence of mucosal breaks.

Results

The 8 endoscopists determined mucosal breaks were present in 79.4 ± 9.5% (67.4%-93.0%) on WLI, and 76.7 ± 12.7% (53.5%-90.7%) on N-NBI. However, the percentage of mucosal breaks on M-NBI was significantly lower at 48.8 ± 17.0% (18.6%-65.1%) (p < 0.05). Intraclass correlation between observers was 0.864 (95% CI 0.793-0.918) for WLI and 0.863 (95% CI 0.791-0.917) for N-NBI but was lower for M-NBI at 0.758 (95% CI 0.631-0.854).

Conclusion

Rates of detection and agreement for mucosal breaks on WLI and N-NBI were high among endoscopists. However, these rates were lower on M-NBI.

Diagnostic Accuracy of High-Grade Intraepithelial Papillary Capillary Loops by Narrow Band Imaging for Early Detection of Oral Malignancy: A Cross-Sectional Clinicopathological Imaging Study

This study aimed to clarify the advantages and disadvantages of conventional visual inspection (CVI), endoscopic white light imaging (WLI), and narrow-band imaging (NBI) and to examine the diagnostic accuracy of intraepithelial papillary capillary loops (IPCL) for the detection of oral squamous cell carcinoma (OSCC). This cross-sectional study included 60 participants with oral mucosal diseases suspected of having oral potentially malignant disorders (OPMDs) or OSCC. The patients underwent CVI, WLI, NBI, and incisional biopsy. Images were evaluated to assess the lesion size, color, texture, and IPCL. Oral lichen planus (OLP) and oral leukoplakia lesions were observed in larger areas with NBI than with WLI; 75.0% were associated with low-grade (Type 0-II) IPCL. Various types of oral leukoplakia were seen; however, all OSCC cases showed high-grade (Type III-IV) IPCL. The diagnostic accuracy of high-grade IPCL for OSCC showed a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 100%, 80.9%, 59.1%, 100%, and 85.0%, respectively. A non-homogeneous lesion with high-grade IPCL strongly suggested malignancy. Overall, our results indicate that WLI and NBI are powerful tools for detecting precancerous and cancerous lesions using IPCL. However, NBI is influenced by mucosal thickness; therefore, image interpretation is important for accurate diagnosis.

Artificial Intelligence in Endoscopy

Artificial intelligence (AI) is rapidly developing in various medical fields, and there is an increase in research performed in the field of gastrointestinal (GI) endoscopy. In particular, the advent of convolutional neural network, which is a class of deep learning method, has the potential to revolutionize the field of GI endoscopy, including esophagogastroduodenoscopy (EGD), capsule endoscopy (CE), and colonoscopy. A total of 149 original articles pertaining to AI (27 articles in esophagus, 30 articles in stomach, 29 articles in CE, and 63 articles in colon) were identified in this review. The main focuses of AI in EGD are cancer detection, identifying the depth of cancer invasion, prediction of pathological diagnosis, and prediction of Helicobacter pylori infection. In the field of CE, automated detection of bleeding sites, ulcers, tumors, and various small bowel diseases is being investigated. AI in colonoscopy has advanced with several patient-based prospective studies being conducted on the automated detection and classification of colon polyps. Furthermore, research on inflammatory bowel disease has also been recently reported. Most studies of AI in the field of GI endoscopy are still in the preclinical stages because of the retrospective design using still images. Video-based prospective studies are needed to advance the field. However, AI will continue to develop and be used in daily clinical practice in the near future. In this review, we have highlighted the published literature along with providing current status and insights into the future of AI in GI endoscopy.

Utility of an artificial intelligence system for classification of esophageal lesions when simulating its clinical use

Previous reports have shown favorable performance of artificial intelligence (AI) systems for diagnosing esophageal squamous cell carcinoma (ESCC) compared with endoscopists. However, these findings don't reflect performance in clinical situations, as endoscopists classify lesions based on both magnified and non-magnified videos, while AI systems often use only a few magnified narrow band imaging (NBI) still images. We evaluated the performance of the AI system in simulated clinical situations. We used 25,048 images from 1433 superficial ESCC and 4746 images from 410 noncancerous esophagi to construct our AI system. For the validation dataset, we took NBI videos of suspected superficial ESCCs. The AI system diagnosis used one magnified still image taken from each video, while 19 endoscopists used whole videos. We used 147 videos and still images including 83 superficial ESCC and 64 non-ESCC lesions. The accuracy, sensitivity and specificity for the classification of ESCC were, respectively, 80.9% [95% CI 73.6-87.0], 85.5% [76.1-92.3], and 75.0% [62.6-85.0] for the AI system and 69.2% [66.4-72.1], 67.5% [61.4-73.6], and 71.5% [61.9-81.0] for the endoscopists. The AI system correctly classified all ESCCs invading the muscularis mucosa or submucosa and 96.8% of lesions ≥ 20 mm, whereas even the experts diagnosed some of them as non-ESCCs. Our AI system showed higher accuracy for classifying ESCC and non-ESCC than endoscopists. It may provide valuable diagnostic support to endoscopists.

Current status of endoscopic detection, characterization and staging of superficial esophageal squamous cell carcinoma

BACKGROUND

This review focuses on the current status of endoscopic detection, characterization and tumour category staging of oesophagealsquamous cell carcinoma.

DETECTION

The diagnostic yield of white-light imaging is limited and narrow-band imaging has demonstrated a better performance for detecting oesophageal cancer. Narrow-band imaging has also shown similar sensitivity and superior specificity to iodine staining.

CHARACTERIZATION

Accurate differentiation between cancerous and non-cancerous lesions can be achieved by magnifying narrow-band imaging or iodine staining with confirmation of a pink-colour sign. A per-patient analysis of a randomized study showed similar sensitivities, specificities and overall accuracies of magnifying narrow-band imaging and iodine staining of 82.2%, 95.1% and 91.2%, and 80.5%, 94.3% and 90.5%, respectively.

TUMOUR-STAGING

The diagnostic capability of endoscopic ultrasonography after conventional and narrow-band imaging in terms of tumour depth was evaluated in a multicentre prospective study. Endoscopic ultrasonography did not significantly improve the accuracy for distinguishing between mucosal or submucosal microinvasive cancer and deeper cancers from 72.9 to 74.0%, suggesting that additional endoscopic ultrasonography did not improve the diagnostic accuracy. In addition, endoscopic ultrasonography increased the incidence of overdiagnosis, defined as a diagnosis of cancer depth greater than the actual depth, by 6.6%. The risk of overdiagnosis by endoscopic ultrasonography was reconfirmed in two systematic reviews.

CONCLUSIONS

Narrow-band imaging is currently considered as the standard modality for the detection and characterization of oesophageal cancer. The risk of overdiagnosis should be considered when applying endoscopic ultrasonography for the evaluation of tumour invasion depth of superficial oesophageal squamous cell carcinoma.

Efficacy of a Third-Generation High-Vision Ultrathin Endoscope for Evaluating Gastric Atrophy and Intestinal Metaplasia in Helicobacter pylori-Eradicated Patients

BACKGROUND

Image-enhanced endoscopy methods such as narrow-band imaging (NBI) are advantageous over white-light imaging (WLI) for detecting gastric atrophy, intestinal metaplasia, and cancer. Although new third-generation high-vision ultrathin endoscopes improve image quality and resolution over second-generation endoscopes, it is unclear whether the former also enhances color differences surrounding atrophy and intestinal metaplasia for endoscopic detection. We compared the efficacy of a new third-generation ultrathin endoscope and an older second-generation endoscope.

METHODS

We enrolled 50 Helicobacter pylori-eradicated patients who underwent transnasal endoscopy with a second-generation and third-generation endoscope (GIF-290N and GIF-1200N, respectively) in our retrospective study. Color differences based on the International Commission on Illumination 1976 (L*, a*, b*) color space were compared between second-generation and third-generation high-vision endoscopes.

RESULTS

Color differences surrounding atrophy produced by NBI on the GIF-1200N endoscope were significantly greater than those on GIF-290N (19.2 ± 8.5 vs. 14.4 ± 6.2, p = 0.001). In contrast, color differences surrounding intestinal metaplasia using both WLI and NBI were similar on GIF-1200N and GIF-290N endoscopes. NBI was advantageous over WLI for detecting intestinal metaplasia on both endoscopes.

CONCLUSIONS

NBI using a third-generation ultrathin endoscope produced significantly greater color differences surrounding atrophy and intestinal metaplasia in H. pylori-eradicated patients compared with WLI.

The characteristics of missed pharyngeal and laryngeal cancers at gastrointestinal endoscopy

Objectives

Understanding the miss rate and characteristics of missed pharyngeal and laryngeal cancers during upper gastrointestinal endoscopy may aid in reducing the endoscopic miss rate of this cancer type. However, little is known regarding the miss rate and characteristics of such cancers. Therefore, the aim of this study was to investigate the upper gastrointestinal endoscopic miss rate of oro-hypopharyngeal and laryngeal cancers, the characteristics of the missed cancers, and risk factors associated with the missed cancers.

Methods

Patients who underwent upper gastrointestinal endoscopy and were pathologically diagnosed with oro-hypopharyngeal and laryngeal squamous cell carcinoma from January 2019 to November 2020 at our institution were retrospectively evaluated. Missed cancers were defined as those diagnosed within 15 months after a negative upper gastrointestinal endoscopy.

Results

A total of 240 lesions were finally included. Eighty-five lesions were classified as missed cancers, and 155 lesions as non-missed cancers. The upper gastrointestinal endoscopic miss rate for oro-hypopharyngeal and laryngeal cancers was 35.4%. Multivariate analysis revealed that a tumor size of &lt;13 mm (odds ratio: 1.96, P=0.026), tumors located on the anterior surface of the epiglottis/valleculae (odds ratio: 2.98, P=0.045) and inside of the pyriform sinus (odds ratio: 2.28, P=0.046) were associated with missed cancers.

Conclusions

This study revealed a high miss rate of oro-hypopharyngeal and laryngeal cancers during endoscopic observations. High-quality upper gastrointestinal endoscopic observation and awareness of missed cancer may help reduce this rate.

Implementation of artificial intelligence in upper gastrointestinal endoscopy

The application of artificial intelligence (AI) using deep learning has significantly expanded in the field of esophagogastric endoscopy. Recent studies have shown promising results in detecting and differentiating early gastric cancer using AI tools built using white light, magnified, or image-enhanced endoscopic images. Some studies have reported the use of AI tools to predict the depth of early gastric cancer based on endoscopic images. Similarly, studies based on using AI for detecting early esophageal cancer have also been reported, with an accuracy comparable to that of endoscopy specialists. Moreover, an AI system, developed to diagnose pharyngeal cancer, has shown promising performance with high sensitivity. These reports suggest that, if introduced for regular use in clinical settings, AI systems can significantly reduce the burden on physicians. This review summarizes the current status of AI applications in the upper gastrointestinal tract and presents directions for clinical practice implementation and future research.

Blue laser imaging identifies endoscopic findings corresponding to metachronous esophageal squamous cell carcinoma

BACKGROUND AND STUDY AIM

This study aimed to evaluate endoscopic findings using non-magnifying blue laser imaging (BLI) to determine the risk factors for metachronous esophageal squamous cell carcinoma (ESCC).

PATIENTS AND METHODS

All consecutive patients who underwent endoscopic submucosal dissection (ESD) for primary superficial ESCC (SESCC) without a history of ESCC between January 2013 and January 2016 were enrolled. Three highly experienced endoscopists investigated seven endoscopic findings using non-magnifying BLI as follows: (1) a brownish area with unclear margin, (2) white flat deposits, (3) multiple foci of dilated vessels, (4) low capillary permeability, (5) multiple glycogenic acanthosis, (6) horizontal lines, and (7) a nonuniform color tone. Furthermore, Lugol-voiding lesions (LVLs) were graded according to the number of LVLs per endoscopic view (A, no lesions; B, 1-9 lesions; C, ≥ 10 lesions).

RESULTS

A total of 102 SESCC patients who underwent ESD were included. Multivariate analyses showed that multiple foci of dilated vessels, low capillary permeability, and a nonuniform color tone were significantly associated with metachronous ESCC (hazard ratio [HR] 2.30; 95% confidence interval [CI] 1.01-5.46; P = 0.049, HR 5.25; 95% CI 1.86-15.01; P = 0.002 and HR 3.17; 95% CI 1.11-9.43; P = 0.032, respectively). The three-year cumulative incidence of metachronous ESCC was significantly higher in patients with low capillary permeability and a nonuniform color tone than in patients without these findings. (41.1% vs. 6.0%, 45.0% vs. 12.7%, respectively, P < 0.001 for both).

CONCLUSION

BLI findings of multiple foci of dilated vessels, low capillary permeability, and a nonuniform color tone in the background esophageal mucosa were risk factors for patients with metachronous ESCC after ESD.

Detection of colorectal lesions during colonoscopy

Owing to its high mortality rate, the prevention of colorectal cancer is of particular importance. The resection of colorectal polyps is reported to drastically reduce colorectal cancer mortality, and examination by endoscopists who had a high adenoma detection rate was found to lower the risk of colorectal cancer, highlighting the importance of identifying lesions. Various devices, imaging techniques, and diagnostic tools aimed at reducing the rate of missed lesions have therefore been developed to improve detection. The distal attachments and devices for improving the endoscopic view angle are intended to help avoid missing blind spots such as folds and flexures in the colon, whereas the imaging techniques represented by image‐enhanced endoscopy contribute to improving lesion visibility. Recent advances in artificial intelligence‐supported detection systems are expected to supplement an endoscopist's eye through the instant diagnosis of the lesions displayed on the monitor. In this review, we provide an outline of each tool and assess its impact on the reduction in the incidence of missed colorectal polyps by summarizing previous clinical research and meta‐analyses. Although useful, the many devices, image‐enhanced endoscopy, and artificial intelligence tools exhibited various limitations. Integrating these tools can improve their shortcomings. Combining artificial intelligence‐based diagnoses with wide‐angle image‐enhanced endoscopy may be particularly useful. Thus, we hope that such tools will be available in the near future.

Texture and color enhancement imaging in magnifying endoscopic evaluation of colorectal adenomas

BACKGROUND

Olympus Corporation has developed texture and color enhancement imaging (TXI) as a novel image-enhancing endoscopic technique.

AIM

To investigate the effectiveness of TXI in identifying colorectal adenomas using magnifying observation.

METHODS

Colorectal adenomas were observed by magnified endoscopy using white light imaging (WLI), TXI, narrow band imaging (NBI), and chromoendoscopy (CE). This study adopted mode 1 of TXI. Adenomas were confirmed by histological examination. TXI visibility was compared with the visibility of WLI, NBI, and CE for tumor margin, and vessel and surface patterns of the Japan NBI expert team (JNET) classification. Three expert endoscopists and three non-expert endoscopists evaluated the visibility scores, which were classified as 1, 2, 3, and 4.

RESULTS

Sixty-one consecutive adenomas were evaluated. The visibility score for tumor margin of TXI (3.47 ± 0.79) was significantly higher than that of WLI (2.86 ± 1.02, P < 0.001), but lower than that of NBI (3.76 ± 0.52, P < 0.001), regardless of the endoscopist's expertise. TXI (3.05 ± 0.79) had a higher visibility score for the vessel pattern of JNET classification than WLI (2.17 ± 0.90, P < 0.001) and CE (2.47 ± 0.87, P < 0.001), but lower visibility score than NBI (3.79 ± 0.47, P < 0.001), regardless of the experience of endoscopists. For the visibility score for the surface pattern of JNET classification, TXI (2.89 ± 0.85) was superior to WLI (1.95 ± 0.79, P < 0.01) and CE (2.75 ± 0.90, P = 0.002), but inferior to NBI (3.67 ± 0.55, P < 0.001).

CONCLUSION

TXI provided higher visibility than WLI, lower than NBI, and comparable to or higher than CE in the magnified observation of colorectal adenomas.

Endoscopic Diagnosis and Treatment of Superficial Esophageal Squamous Cell Cancer: Present Status and Future Perspectives

This review provides information regarding the preoperative examinations, indications for endoscopic resection (ER), and curability assessment in subjects with superficial esophageal squamous cell carcinoma (SCC). Narrow-band imaging (NBI) is a more sensitive modality for detecting esophageal cancer than conventional observation, and esophageal observation using NBI is thus recommended for the detection of superficial esophageal cancer. It is also important to adjust the volume of air in the esophagus during observation. Workup by non-magnifying followed by magnifying endoscopy is a common process for diagnosing the invasion depth of superficial esophageal SCCs in Japan. Endoscopic ultrasonography carries a risk of overdiagnosis, and its routine use is therefore not recommended. The Japanese endoscopic submucosal dissection/endoscopic mucosal resection guidelines for esophageal cancer considered the indications for ER based on the results of studies focusing on clinical MM/SM1 cancers, and concluded that clinical MM/SM1 carcinomas, except circumferential carcinoma, were an indication for ER. The curative effect of ER should be assessed based on histologic examination of the resected specimens. ER should be conducted based on a thorough understanding of the preoperative diagnosis, indication, curability, and additional treatment of esophageal SCC.

Electronic chromo-endoscopy: technical details and a clinical perspective

Precise endoscopic assessment is necessary to detect neoplastic changes in an early stage. Electronic or virtual chromo-endoscopy (ECE) is an alternative to conventional dye-based chromo-endoscopy which markedly improves capillary pattern and hence can detect micro-vessel morphological changes of early neoplasia to target biopsies and aid in diagnosis. The clinical significance increased after the advent of endoscopic treatment modalities like ESD/EMR which requires precise delineation of extent and depth of lesion. Most of the studies have used narrow-band imaging (NBI) (Olympus Medical Systems Tokyo, Japan), although data from i-SCAN (PENTAX Endoscopy, Tokyo, Japan) and flexible spectral imaging color enhancement (FICE) (Fujinon, Fujifilm Medical Co, Saitama, Japan) are emerging. Electronic chromo-endoscopy is convenient compared to dye-based chromo-endoscopy in the sense that it is available at the push of a button in endoscope and reduces procedure time substantially with comparable efficacy. Scope of this review is to discuss available electronic chromo-endoscopy modalities and their role in the diagnosis, surveillance, and management of early GI neoplasia.

A Five-Parameter Logistic Model to Predict the Possibility of Misdiagnosis for Improving the Specificity of Lugol Chromoendoscopy in the Diagnosis of Esophageal Neoplastic Lesions

Background

Lugol chromoendoscopy (LCE) is a technique that is inexpensive and convenient for screening esophageal neoplastic lesions. However, the specificity of LCE is limited. The purpose of this study was to determine the risk characteristics of lesions related to false-positive results for LCE.

Methods

In this retrospective study, 871 lesions in 773 patients scheduled for LCE in Wuhan Union Hospital and First Affiliated Hospital of Shihezi University between April 2013 and October 2018 were enrolled. The 871 lesions were used to determine the diagnostic performance of LCE for detecting esophageal neoplastic lesions and were divided into an LCE-positive group (627 lesions) and an LCE-negative group (244 lesions). Six hundred and twenty-seven unstained/understained lesions from 563 patients were used to determine the significant risk factors for misdiagnosis of neoplasms by LCE. Among them, 358 lesions and 269 lesions were classified into the misdiagnosed group and correctly diagnosed group, respectively. A multivariate logistic regression analysis was conducted for suspected esophageal neoplastic lesions during the LCE examination.

Results

The sensitivity, specificity, and overall accuracy for LCE were 100%, 40.5%, and 58.9%, respectively. Among 13 characteristics of lesions, lesions with branching vascular network (OR 4.53, 95% CI 2.23–9.21, p < 0.001), smooth lesions (OR 2.40, 95% CI 1.38–4.18, p = 0.002) under white light endoscopy (WLE), lesions with a size < 5 mm (OR 3.06, 95% CI 1.38–6.78, p = 0.006), ill-demarcated lesions (OR 7.83, 95% CI 4.59–13.37, p < 0.001), and pink color sign (PCS)-negative (OR 4.04, 95% CI 2.38–6.84, p < 0.001) lesions after reaction with iodine solution were independent risk factors for misdiagnosis as neoplastic lesions by LCE.

Conclusion

LCE has a high sensitivity but limited specificity for screening esophageal neoplastic lesions. For unstained or understained lesions, branching vascular network or smooth appearance under WLE, a size < 5 mm in diameter, ill-demarcated, or PCS-negative lesions after staining are related to the misdiagnosis of esophageal neoplastic lesions by LCE based on logistic regression. The multivariate logistic model may be used to predict the possibility of misdiagnosis and help improve the specificity of LCE in diagnosing esophageal neoplastic lesions.

Artificial intelligence for detecting superficial esophageal squamous cell carcinoma under multiple endoscopic imaging modalities: A multicenter study

BACKGROUND AND AIM

Diagnosis of esophageal squamous cell carcinoma (ESCC) is complicated and requires substantial expertise and experience. This study aimed to develop an artificial intelligence (AI) system for detecting superficial ESCC under multiple endoscopic imaging modalities.

METHODS

Endoscopic images were retrospectively collected from West China Hospital, Sichuan University as a training dataset and an independent internal validation dataset. Images from other four hospitals were used as an external validation dataset. The AI system was compared with 11 experienced endoscopists. Furthermore, videos were collected to assess the performance of the AI system.

RESULTS

A total of 53 933 images from 2621 patients and 142 videos from 19 patients were used to develop and validate the AI system. In the internal and external validation datasets, the performance of the AI system under all or different endoscopic imaging modalities was satisfactory, with sensitivity of 92.5-99.7%, specificity of 78.5-89.0%, and area under the receiver operating characteristic curves of 0.906-0.989. The AI system achieved comparable performance with experienced endoscopists. Regarding superficial ESCC confined to the epithelium, the AI system was more sensitive than experienced endoscopists on white-light imaging (90.8% vs 82.5%, P = 0.022). Moreover, the AI system exhibited good performance in videos, with sensitivity of 89.5-100% and specificity of 73.7-89.5%.

CONCLUSIONS

We developed an AI system that showed comparable performance with experienced endoscopists in detecting superficial ESCC under multiple endoscopic imaging modalities and might provide valuable support for inexperienced endoscopists, despite requiring further evaluation.

Endoscopic Submucosal Dissection for Superficial Pharyngeal Carcinoma Is Effective and Safe

BACKGROUND

Endoscopic submucosal dissection (ESD) of superficial squamous epithelial lesions at the pharynx is still a challenge for most endoscopists due to the limited working space and inexperience. The aim of this study was to evaluate the outcomes of ESD for superficial pharyngeal carcinomas.

METHODS

A total of 30 superficial carcinomas at the pharynx in 27 consecutively treated patients were included. The rates of en bloc resection, complete resection, major complications, local recurrence, and metastasis were evaluated retrospectively as the therapeutic outcomes.

RESULTS

The en bloc and complete resection rates were respectively 100% and 93.3%. No bleeding, perforation, or dyspnea during or after the ESD procedure occurred. There was 1 patient with emphysema. The median hospital stay was 6 days. During the follow-up period of 1 year, 1 patient had neck lymph node metastasis.

CONCLUSION

ESD is effective and safe for resection of superficial carcinomas at the pharynx, with a high complete resection rate and favorable outcomes.

Effect of adding magnifying BLI, magnifying NBI, and iodine staining to white light imaging in diagnosis of early esophageal cancer

Background and study aims  We investigated the effect of adding magnifying blue laser imaging (BLI), magnifying narrow-band imaging (NBI), and iodine staining to white light imaging in diagnosis of early esophageal squamous cell carcinoma (EESCC) in high-risk patients. Patients and methods  Between May 2013 and March 2016, two parallel prospective cohorts of patients received either primary WLI followed by NBI-magnifying endoscopy (ME) or primary WLI followed by BLI-ME, were studied. At the end of screening, both groups underwent iodine staining. The percentage of patients with newly detected esophageal malignant lesions in each group and the diagnostic ability of image-enhanced endoscopy (IEE)-ME were evaluated. Results  There are 258 patients assigned to the NBI-ME group and 254 patients assigned to the BLI-ME group. The percentage of patients with one or more malignant lesions detected in the WLI + NBI-ME examination was similar in the WLI + BLI-ME examination (15 of 258 patients or 5.81 % vs. 14 of 254 patients or 5.51 %). However, four of 19 lesions in the NBI-ME group and six of 21 lesions in the BLI-ME group were overlooked and were detected by iodine staining. NBI-ME and BLI-ME showed similar accuracy in differentiation of cancerous lesions from non-cancerous lesions in diagnosis of EESCC (NBI/BLI: sensitivity, 87.5/89.5; specificity, 78.9/76.6; accuracy, 80.8/79.5; positive predictive value, 53.8/53.1; negative predictive value, 95.7/96.1). Conclusions  Both NBI and BLI were useful for detection of EESCC. However, because some lesions were overlooked by even NBI and BLI, high-risk patients may benefit from use of iodine staining during endoscopic screening of EESCC (UMIN000023596).

Narrow band imaging in early diagnosis of laryngopharyngeal malignant and premalignant lesions

OBJECTIVES

(1) To assess the diagnostic accuracy of narrow-band imaging (NBI) in the assessment of benign, premalignant, and malignant vocal fold lesions. (2) To evaluate the diagnostic value of NBI in detection of recurrence in upper aero-digestive tract malignancy.

METHODS

This was a prospective, observational study done between December 2018- November 2019 in the Department of Otolaryngology. One hundred six patients of suspected benign, premalignant, malignant lesions of larynx and hypopharynx along with recurrence cases of upper aerodigestive tract malignancy who have completed chemoradiation therapy. All patients were subjected to white light endoscopy (WLE), NBI, and biopsy for histopathological diagnosis. In WLE, laryngeal lesions were classified into three types: malignant, suspected malignant, and benign. NBI images were classified into 5 types based on the intrapapillary capillary loop (IPCL) patterns: Type I-IV were considered benign and Type V lesion was considered malignant. At the end, WLE and NBI findings were correlated with histopathological reports.

RESULTS

The diagnostic accuracy of NBI in diagnosing benign, premalignant, and malignant lesions is significantly better than WLE. The sensitivity of NBI in detecting malignant lesions is significantly greater than WLE. NBI has proved to be of great value in identifying lesions that could be missed by WLE alone, as combined sensitivity of NBI and WLE is significantly higher than WLE alone.

CONCLUSION

NBI is an excellent technique for early detection of laryngopharyngeal malignancies with significantly higher sensitivity than WLE alone.

Efficacy of endoscopic ultrasonography in evaluating tumor thickness in patients with superficial pharyngeal carcinoma: A pilot study

OBJECTIVES

A histopathological tumor thickness of ≥1000 μm has been reported as one of many risk factors for recurrent lymph node metastasis in superficial pharyngeal cancer (SPC). However, methods for assessing this risk factor preoperatively have not yet been established. Hence, the current study aimed to evaluate the efficacy of endoscopic ultrasonography (EUS) in measuring tumor thickness preoperatively in patients with SPC.

METHODS

This single-center retrospective study included 44 consecutive patients with 47 lesions who underwent endoscopic submucosal dissection (ESD). Prior to surgery, EUS examination was performed while under general anesthesia. Further, microvascular irregularity in the target lesion was evaluated using the Japan Esophageal Society (JES) magnification endoscopic classification system.

RESULTS

A significant correlation was noted between histopathological and EUS tumor thickness (Spearman's correlation r == 0.879, p < 0.001). In tumors ≥1000 µm thick on histopathology, the cutoff value for EUS tumor thickness was 2.6 mm, and the following values were obtained: sensitivity, 100%; specificity, 81.8%; positive predictive value (PPV), 70%; negative predictive value (NPV), 100%; and accuracy, 87.2%. In B2 lesions ≥1000-μm thick, the following values were obtained: sensitivity, 85.7%; specificity, 90.9%; PPV, 80%; NPV, 93.8%; and accuracy, 89.4%. The diagnostic accuracy rate of combined EUS and the JES magnifying endoscopic classification system was 95.7%.

CONCLUSIONS

Tumor thickness assessed using EUS was effective in diagnosing histopathological tumor thickness of ≥1000 μm. The combined use of EUS and the JES magnifying endoscopic classification system may be useful for assessing preoperative risk factors for lymph node metastasis in SPC.

Characteristics of superficial esophageal squamous cell carcinomas undetectable with narrow-band imaging endoscopy

Background

The detection rate of narrow-band imaging (NBI) for superficial esophageal squamous cell carcinoma (SESCC), including high-grade intraepithelial neoplasia, is significantly higher than that of white-light endoscopy. However, there are SESCCs that are undetectable by NBI but detectable by Lugol chromoendoscopy (LCE) and the characteristics of these SESCCs are still unknown. Thus, this study aimed to clarify the characteristics of SESCC that are undetectable using NBI.

Methods

Patients with current SCC or a history of SCC in the head and neck or in the esophagus were enrolled. The inspection of the esophagus was initiated by NBI, followed by LCE. Biopsies were taken of all suspected SESCC lesions during NBI observation and Lugol-voiding lesions (LVLs) that were irregularly shaped and >5 mm and/or pink in color during LCE observation. The characteristics of SESCC that were undetectable with NBI were statistically analysed.

Results

Overall, 147 lesions in 105 cases were histologically diagnosed as SESCC. Twenty in 15 cases were NBI-undetectable lesions, all of which were macroscopic flat type (0-IIb). The median sizes of the NBI-undetectable lesions and NBI-detectable lesions were both 15 mm (P = 0.47). Multivariate analysis revealed independent factors for NBI-undetectable lesions such as numerous irregularly shaped LVLs (odds ratio [OR]: 4.94, 95% confidence interval [CI]: 1.39–17.5, P < 0.05) and anterior wall position (OR: 4.99, 95% CI: 1.58–15.8, P < 0.05).

Conclusions

The detection of SESCCs with NBI is challenging when lesions are morphologically completely flat, in cases with numerous irregularly shaped LVLs, and if located at the anterior wall.

Diagnostic yield of fourth-generation endocytoscopy for esophageal squamous lesions using a modified endocytoscopic classification

OBJECTIVES

Endocytoscopy (EC) is an ultra-high magnification endoscopy designed to provide in vivo histologic assessment. This study aimed to evaluate the diagnostic yield of the newly developed fourth-generation EC for esophageal squamous lesions by using a modified EC classification.

METHODS

A total of 2548 EC images of 57 esophageal targeted areas between June 2015 and October 2017 were retrospectively collected. Two lesions with low-quality images were excluded. Only EC images were independently reviewed by two expert and two non-expert endoscopists. The lesions were classified according to a three-tier modified EC classification. We used a multilevel logistic regression to analyze the data.

RESULTS

The sensitivity and specificity of diagnosing non-squamous cell cancer (SCC) vs SCC were 82.5% and 83.0% by the experts; 90.1% and 75.0% by non-experts. The interobserver agreement among the four raters was good (kappa statistic 0.59). The diagnostic accuracy of experts and non-experts was similar (P = 0.16 for specificity and P = 0.20 for sensitivity). The sensitivity and specificity of EC for non-neoplasia vs neoplasia were 88.7% and 74.6% by experts; 90.3 and 52.1% by non-experts. The interobserver agreement among the four raters was moderate (kappa statistic 0.44). The specificity of experts was higher compared to non-experts, although the difference did not reach statistical significance (P = 0.08 for specificity and P = 0.93 for sensitivity).

CONCLUSIONS

Fourth-generation EC offers acceptable diagnostic accuracy and reliability in both experts and non-experts, especially when diagnosing SCC lesions.

Artificial intelligence diagnostic system predicts multiple Lugol-voiding lesions in the esophagus and patients at high risk for esophageal squamous cell carcinoma

BACKGROUND

It is known that an esophagus with multiple Lugol-voiding lesions (LVLs) after iodine staining is high risk for esophageal cancer; however, it is preferable to identify high-risk cases without staining because iodine causes discomfort and prolongs examination times. This study assessed the capability of an artificial intelligence (AI) system to predict multiple LVLs from images that had not been stained with iodine as well as patients at high risk for esophageal cancer.

METHODS

We constructed the AI system by preparing a training set of 6634 images from white-light and narrow-band imaging in 595 patients before they underwent endoscopic examination with iodine staining. Diagnostic performance was evaluated on an independent validation dataset (667 images from 72 patients) and compared with that of 10 experienced endoscopists.

RESULTS

The sensitivity, specificity, and accuracy of the AI system to predict multiple LVLs were 84.4 %, 70.0 %, and 76.4 %, respectively, compared with 46.9 %, 77.5 %, and 63.9 %, respectively, for the endoscopists. The AI system had significantly higher sensitivity than 9/10 experienced endoscopists. We also identified six endoscopic findings that were significantly more frequent in patients with multiple LVLs; however, the AI system had greater sensitivity than these findings for the prediction of multiple LVLs. Moreover, patients with AI-predicted multiple LVLs had significantly more cancers in the esophagus and head and neck than patients without predicted multiple LVLs.

CONCLUSION

The AI system could predict multiple LVLs with high sensitivity from images without iodine staining. The system could enable endoscopists to apply iodine staining more judiciously.

Usefulness of an artificial intelligence system for the detection of esophageal squamous cell carcinoma evaluated with videos simulating overlooking situation

OBJECTIVES

Artificial intelligence (AI) systems have shown favorable performance in the detection of esophageal squamous cell carcinoma (ESCC). However, previous studies were limited by the quality of their validation methods. In this study, we evaluated the performance of an AI system with videos simulating situations in which ESCC has been overlooked.

METHODS

We used 17,336 images from 1376 superficial ESCCs and 1461 images from 196 noncancerous and normal esophagi to construct the AI system. To record validation videos, the endoscope was passed through the esophagus at a constant speed without focusing on the lesion to simulate situations in which ESCC has been missed. Validation videos were evaluated by the AI system and 21 endoscopists.

RESULTS

We prepared 100 video datasets, including 50 superficial ESCCs, 22 noncancerous lesions, and 28 normal esophagi. The AI system had sensitivity of 85.7% (54 of 63 ESCCs) and specificity of 40%. Initial evaluation by endoscopists conducted with plain video (without AI support) had average sensitivity of 75.0% (47.3 of 63 ESCC) and specificity of 91.4%. Subsequent evaluation by endoscopists was conducted with AI assistance, which improved their sensitivity to 77.7% (P = 0.00696) without changing their specificity (91.6%, P = 0.756).

CONCLUSIONS

Our AI system had high sensitivity for the detection of ESCC. As a support tool, the system has the potential to enhance detection of ESCC without reducing specificity. (UMIN000039645).